FlowiseAI / Flowise

Drag & drop UI to build your customized LLM flow
https://flowiseai.com
Apache License 2.0
29.82k stars 15.37k forks source link

[BUG] Upsert - Error: vectorsService.upsertVector - Error: TypeError: Cannot read properties of undefined (reading '0') #3113

Open ApplicationError opened 2 weeks ago

ApplicationError commented 2 weeks ago

Describe the bug Error: vectorsService.upsertVector - Error: TypeError: Cannot read properties of undefined (reading '0')

I've setup a new Flowise project with the following components & configuration:

Conversational Retrieval QA Chain

Check I go to "upsert" the data to Pinecone I get that error message. Error: vectorsService.upsertVector - Error: TypeError: Cannot read properties of undefined (reading '0')

To Reproduce Steps to reproduce the behavior:

1.) Setup as outlined above 2.) Save project 3.) Click on green "upsert" icon 4.) Click on green "upsert" button

Expected behavior The data from the PDF and the TXT file to be stored in the Pinecone vector store.

Setup

Render.com Logs

error 2024-08-29 19:57:30 [ERROR]: TypeError: Cannot read properties of undefined (reading '0') error Error: TypeError: Cannot read properties of undefined (reading '0') info at Pinecone_VectorStores.upsert (/usr/src/packages/components/dist/nodes/vectorstores/Pinecone/Pinecone.js:80:27) info at process.processTicksAndRejections (node:internal/process/task_queues:95:5) info at async buildFlow (/usr/src/packages/server/dist/utils/index.js:415:37) info at async upsertVector (/usr/src/packages/server/dist/utils/upsertVector.js:126:32) info at async Object.upsertVectorMiddleware (/usr/src/packages/server/dist/services/vectors/index.js:9:16) info at async createInternalUpsert (/usr/src/packages/server/dist/controllers/vectors/index.js:28:29) error 2024-08-29 19:57:30 [ERROR]: [server]: Error: Error: TypeError: Cannot read properties of undefined (reading '0') error Error: Error: TypeError: Cannot read properties of undefined (reading '0') info at buildFlow (/usr/src/packages/server/dist/utils/index.js:493:19) info at process.processTicksAndRejections (node:internal/process/task_queues:95:5) info at async upsertVector (/usr/src/packages/server/dist/utils/upsertVector.js:126:32) info at async Object.upsertVectorMiddleware (/usr/src/packages/server/dist/services/vectors/index.js:9:16) info at async createInternalUpsert (/usr/src/packages/server/dist/controllers/vectors/index.js:28:29)

2024-08-29 at 4 14 PM

HenryHengZJ commented 2 weeks ago

If you switch to other embeddings model it should works. Seen this issue with voyage embeddings, mostly due to the rate limit

ApplicationError commented 2 weeks ago

If you switch to other embeddings model it should works. Seen this issue with voyage embeddings, mostly due to the rate limit

Thank you very much for the reply. Do you have any recommendations for embedding models that would work best?

Vortigern-source commented 1 week ago

I have a similar issue, Im not sure what embedding to use with groq if VoyageAI isnt working the best

Vortigern-source commented 1 week ago

What embeddings can be used that are free? Also are you saying that reducing the rate limit option should fix it?

jockharkness commented 6 days ago

If you switch to other embeddings model it should works. Seen this issue with voyage embeddings, mostly due to the rate limit

I have a similar setup (except using in-memory vector store) and the exact same error message.

I changed to OpenAI embeddings and it didn't fix the issue, still getting the same error message